Differential Operator in Seizure Detection

TL;DR

This paper presents a fast, linear-time seizure detection method using differential operators and novel parameters to improve accuracy in analyzing epileptic ECoG signals, with minimal false detections.

Contribution

Introduces a novel seizure detection approach utilizing normalized exponential derivatives and patient-specific thresholding, achieving high accuracy and speed.

Findings

High ROC AUC indicates excellent detection performance

Method reduces false detection rate significantly

All operations are computationally efficient and linear in time

Abstract

Differential operators can detect significant changes in signals. This has been utilized to enhance the contrast of the seizure signatures in depth EEG or ECoG. We have actually taken normalized exponential of absolute value of single or double derivative of epileptic ECoG. Variance operation has been performed to automatically detect seizures. A novel method for determining the duration of seizure has also been proposed. Since all operations take only linear time, the whole method is extremely fast. Seven novel parameters have been introduced whose patient specific thresholding brings down the rate of false detection to a bare minimum. Results of implementation on the ECoG data of four epileptic patients have been reported with an ROC curve analysis. High value of the area under the ROC curve indicates excellent detection performance.